{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:3C2NCFHZIN4EQRJ7W6N5ZWL4V7","short_pith_number":"pith:3C2NCFHZ","canonical_record":{"source":{"id":"1708.04133","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-10T19:20:15Z","cross_cats_sorted":[],"title_canon_sha256":"78007a75ce0985bbc7364d18489f0765150816c92d9ab97b99f74cdbc107c575","abstract_canon_sha256":"3fd9fbf2c2b7a3c6ae2120fa2d69e610715ef4fc1d417809fa5aa046cd1441f1"},"schema_version":"1.0"},"canonical_sha256":"d8b4d114f9437848453fb79bdcd97cafe97c49b557a707a9d14be522a4e2891c","source":{"kind":"arxiv","id":"1708.04133","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.04133","created_at":"2026-05-18T00:38:06Z"},{"alias_kind":"arxiv_version","alias_value":"1708.04133v1","created_at":"2026-05-18T00:38:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.04133","created_at":"2026-05-18T00:38:06Z"},{"alias_kind":"pith_short_12","alias_value":"3C2NCFHZIN4E","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3C2NCFHZIN4EQRJ7","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3C2NCFHZ","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:3C2NCFHZIN4EQRJ7W6N5ZWL4V7","target":"record","payload":{"canonical_record":{"source":{"id":"1708.04133","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-10T19:20:15Z","cross_cats_sorted":[],"title_canon_sha256":"78007a75ce0985bbc7364d18489f0765150816c92d9ab97b99f74cdbc107c575","abstract_canon_sha256":"3fd9fbf2c2b7a3c6ae2120fa2d69e610715ef4fc1d417809fa5aa046cd1441f1"},"schema_version":"1.0"},"canonical_sha256":"d8b4d114f9437848453fb79bdcd97cafe97c49b557a707a9d14be522a4e2891c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:06.994479Z","signature_b64":"GfjGhaWKoDd9U5gwSL3cmygWl1bmAVX1Dsir4sXvRZWfhjd4FVNMti5unaFxUuuDLK2/AxB5aHeEpAe6pNxWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8b4d114f9437848453fb79bdcd97cafe97c49b557a707a9d14be522a4e2891c","last_reissued_at":"2026-05-18T00:38:06.994016Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:06.994016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1708.04133","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:38:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DENyPefp8ClDqLhIPqB+Wr6vpeGulzkTwMS8CE1AUW0wD4/mVe43Oi7Vtwj1Y2ML2iq9T+kAAiZujgqhVPtrCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T14:03:44.931909Z"},"content_sha256":"48216b9b55bf06441ca6e9b5a303f3bb7e8e312caf9dd8e499f8458b399cdb04","schema_version":"1.0","event_id":"sha256:48216b9b55bf06441ca6e9b5a303f3bb7e8e312caf9dd8e499f8458b399cdb04"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:3C2NCFHZIN4EQRJ7W6N5ZWL4V7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Doina Precup, Maziar Gomrokchi, Peter Henderson, Riashat Islam","submitted_at":"2017-08-10T19:20:15Z","abstract_excerpt":"Policy gradient methods in reinforcement learning have become increasingly prevalent for state-of-the-art performance in continuous control tasks. Novel methods typically benchmark against a few key algorithms such as deep deterministic policy gradients and trust region policy optimization. As such, it is important to present and use consistent baselines experiments. However, this can be difficult due to general variance in the algorithms, hyper-parameter tuning, and environment stochasticity. We investigate and discuss: the significance of hyper-parameters in policy gradients for continuous c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.04133","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:38:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AqA2XNlkvYLrO5M32p5k6AxM1hE805L+uPXPDZYAZ02xjiu+12cByl1ERTfJsBBq6u75dC+HYCFmDj0/SCq/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-31T14:03:44.932466Z"},"content_sha256":"659a10a43025974716de02e1948fa54239bd4ffa67d707ee07bf52a524b270fc","schema_version":"1.0","event_id":"sha256:659a10a43025974716de02e1948fa54239bd4ffa67d707ee07bf52a524b270fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3C2NCFHZIN4EQRJ7W6N5ZWL4V7/bundle.json","state_url":"https://pith.science/pith/3C2NCFHZIN4EQRJ7W6N5ZWL4V7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3C2NCFHZIN4EQRJ7W6N5ZWL4V7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-31T14:03:44Z","links":{"resolver":"https://pith.science/pith/3C2NCFHZIN4EQRJ7W6N5ZWL4V7","bundle":"https://pith.science/pith/3C2NCFHZIN4EQRJ7W6N5ZWL4V7/bundle.json","state":"https://pith.science/pith/3C2NCFHZIN4EQRJ7W6N5ZWL4V7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3C2NCFHZIN4EQRJ7W6N5ZWL4V7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:3C2NCFHZIN4EQRJ7W6N5ZWL4V7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3fd9fbf2c2b7a3c6ae2120fa2d69e610715ef4fc1d417809fa5aa046cd1441f1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-10T19:20:15Z","title_canon_sha256":"78007a75ce0985bbc7364d18489f0765150816c92d9ab97b99f74cdbc107c575"},"schema_version":"1.0","source":{"id":"1708.04133","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1708.04133","created_at":"2026-05-18T00:38:06Z"},{"alias_kind":"arxiv_version","alias_value":"1708.04133v1","created_at":"2026-05-18T00:38:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.04133","created_at":"2026-05-18T00:38:06Z"},{"alias_kind":"pith_short_12","alias_value":"3C2NCFHZIN4E","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"3C2NCFHZIN4EQRJ7","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"3C2NCFHZ","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:659a10a43025974716de02e1948fa54239bd4ffa67d707ee07bf52a524b270fc","target":"graph","created_at":"2026-05-18T00:38:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Policy gradient methods in reinforcement learning have become increasingly prevalent for state-of-the-art performance in continuous control tasks. Novel methods typically benchmark against a few key algorithms such as deep deterministic policy gradients and trust region policy optimization. As such, it is important to present and use consistent baselines experiments. However, this can be difficult due to general variance in the algorithms, hyper-parameter tuning, and environment stochasticity. We investigate and discuss: the significance of hyper-parameters in policy gradients for continuous c","authors_text":"Doina Precup, Maziar Gomrokchi, Peter Henderson, Riashat Islam","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-10T19:20:15Z","title":"Reproducibility of Benchmarked Deep Reinforcement Learning Tasks for Continuous Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.04133","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:48216b9b55bf06441ca6e9b5a303f3bb7e8e312caf9dd8e499f8458b399cdb04","target":"record","created_at":"2026-05-18T00:38:06Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3fd9fbf2c2b7a3c6ae2120fa2d69e610715ef4fc1d417809fa5aa046cd1441f1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-08-10T19:20:15Z","title_canon_sha256":"78007a75ce0985bbc7364d18489f0765150816c92d9ab97b99f74cdbc107c575"},"schema_version":"1.0","source":{"id":"1708.04133","kind":"arxiv","version":1}},"canonical_sha256":"d8b4d114f9437848453fb79bdcd97cafe97c49b557a707a9d14be522a4e2891c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8b4d114f9437848453fb79bdcd97cafe97c49b557a707a9d14be522a4e2891c","first_computed_at":"2026-05-18T00:38:06.994016Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:38:06.994016Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GfjGhaWKoDd9U5gwSL3cmygWl1bmAVX1Dsir4sXvRZWfhjd4FVNMti5unaFxUuuDLK2/AxB5aHeEpAe6pNxWDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:38:06.994479Z","signed_message":"canonical_sha256_bytes"},"source_id":"1708.04133","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:48216b9b55bf06441ca6e9b5a303f3bb7e8e312caf9dd8e499f8458b399cdb04","sha256:659a10a43025974716de02e1948fa54239bd4ffa67d707ee07bf52a524b270fc"],"state_sha256":"d7100e635dfc92afb1fee7982f26c7c3dfc9fd22e0ed1df6552fd6d2f1b21745"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yv5r6PMDz+oLQrYaKJAADoUXI0zTLk+RQrPsTDtxgqdg3bht5QGIecsvWYZiV8duQWeFt26k/RMgUkLZ7wvmCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-31T14:03:44.935459Z","bundle_sha256":"78d4a36cb173dd907799eec6771c7003627239a4a713aebc4491e7727070abae"}}